@article{amodelfreelearningalgorithmforinfinite,
  title = {A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret},
  author = {Mehdi Jafarnia-Jahromi and Chen-Yu Wei and Rahul Jain and Haipeng Luo},
  year = {2020},
  eprint = {2006.04354},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2006.04354v2},
}